Yi-Hong Lyu c8cd36da01 Resize optimization for all architectures (#11956) ... With this patch, it optimizes Resize when the input X is 4D int8/uint8 tensor and the mode is linear by: * Transforming NCHW Resize to NHWC variant * Using the NHWC Resize kernel without floating-point computation It improves DeepLab V3 with uint8 quantization by 19% on X64. It also improves Resize of DeepLab V3 with int8 quantization by 15%~18% on X64.		2022-06-29 09:19:19 -07:00
..
optimizer_api.h	Update ONNX to 1.12 (#11924)	2022-06-21 17:19:52 -07:00
optimizer_api_impl.cc	NHWC Resize optimization (#11825)	2022-06-17 11:00:36 -07:00
optimizer_utils.h	EP factory creation cleanup and enhancements. (#11798)	2022-06-16 07:01:41 +10:00
ort_transpose_optimizer.cc	Add support for opset 16 to transpose optimizer. (#10841)	2022-03-12 08:50:55 +10:00
ort_transpose_optimizer.h	Fix clash between QDQ propagation and TransposeOptimizer (#11636)	2022-06-03 16:16:35 -07:00
transpose_optimizer.cc	Resize optimization for all architectures (#11956)	2022-06-29 09:19:19 -07:00